© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 141789
    Prev
    Next
    INDEX
    Explanations

    language detection

    np_acts-logits-general · gemini-2.5-flash-lite

    parentheses and word start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     remedy
    0.44
     cure
    0.44
     crater
    0.44
    :.
    0.43
     molecule
    0.43
     magnified
    0.43
     simpler
    0.41
    向下
    0.40
    bell
    0.40
     species
    0.40
    POSITIVE LOGITS
     เจ้า
    0.52
     親
    0.49
    妏
    0.49
     kteří
    0.49
    üren
    0.48
    󠁬
    0.48
     którzy
    0.48
     สอน
    0.47
     線
    0.47
    ądź
    0.47
    Activations Density 0.000%

    No Known Activations